BlitzNet: A Real-Time Deep Network for Scene Understanding

Nikita Dvornik, Konstantin Shmelkov, Julien Mairal, Cordelia Schmid

ICCV 2017

doi:10.1109/ICCV.2017.447 /iccv/2017/dvornik2017iccv-blitznet/

Abstract

Real-time scene understanding has become crucial in many applications such as autonomous driving. In this paper, we propose a deep architecture, called BlitzNet, that jointly performs object detection and semantic segmentation in one forward pass, allowing real-time computations. Besides the computational gain of having a single network to perform several tasks, we show that object detection and semantic segmentation benefit from each other in terms of accuracy. Experimental results for VOC and COCO datasets show state-of-the-art performance for object detection and segmentation among real time systems.

PDF ICCV Semantic Scholar

Cite

Text

Dvornik et al. "BlitzNet: A Real-Time Deep Network for Scene Understanding." International Conference on Computer Vision, 2017. doi:10.1109/ICCV.2017.447

Markdown

[Dvornik et al. "BlitzNet: A Real-Time Deep Network for Scene Understanding." International Conference on Computer Vision, 2017.](https://mlanthology.org/iccv/2017/dvornik2017iccv-blitznet/) doi:10.1109/ICCV.2017.447

BibTeX

@inproceedings{dvornik2017iccv-blitznet,
  title     = {{BlitzNet: A Real-Time Deep Network for Scene Understanding}},
  author    = {Dvornik, Nikita and Shmelkov, Konstantin and Mairal, Julien and Schmid, Cordelia},
  booktitle = {International Conference on Computer Vision},
  year      = {2017},
  doi       = {10.1109/ICCV.2017.447},
  url       = {https://mlanthology.org/iccv/2017/dvornik2017iccv-blitznet/}
}